Merit Write Purchases

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

The description states it does not execute changes and returns preview details plus a confirmation_code, which matches the readOnlyHint annotation. It adds context about return values and the workflow with the confirm sibling, going beyond the annotation's simple read-only flag.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is extremely concise: two sentences and one bullet point. It front-loads the critical preview behavior and action, with no wasted words.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given 9 parameters and no output schema, the description is incomplete. It lacks details on other parameters, expected values, or the structure of the intended operation details. The agent would need additional knowledge to use this tool effectively.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

With 0% schema description coverage, the description should compensate by explaining key parameters, but it only mentions 'action' and 'purchase_invoice_create'. It does not describe other parameters (id, filters, payload, etc.), leaving the agent without guidance on how to construct inputs.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states it is a preview-only write tool that creates purchase invoices and returns a confirmation_code for a sibling confirm tool. It distinguishes itself from the confirm sibling and other write tools by highlighting its preview nature.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description explicitly says 'Preview-only write tool. Does not execute changes; returns intended operation details and a confirmation_code for merit_write_purchases_confirm.' This provides clear guidance on when to use (for previewing) and implies the confirm tool for execution. However, it does not explicitly state when not to use it or list alternatives among siblings.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.